1 February 1991 Multiresolution segmentation of forward-looking IR and SAR imagery using neural networks
Author Affiliations +
Proceedings Volume 1381, Intelligent Robots and Computer Vision IX: Algorithms and Techniques; (1991) https://doi.org/10.1117/12.25191
Event: Advances in Intelligent Robotics Systems, 1990, Boston, MA, United States
Abstract
A neural network approach to segmentation of forward looking infrared and synthetic aperture radar imagery is presented. This approach integrates three stages of processing. First a wavelet transform of the image is performed by projection of the image onto a set of 2-D Gabor functions. This results in a multiple-resolution decomposition of the image into oriented spatial frequency channels. Scond a neural network optimization procedure is used to estimate the wavelet transform coefficients. The third stage involves a segmentation technique that has been shown to work well on textures that human subjects readily segment into regions. Although the approach is still under development preliminary results are promising. The direction of further research efforts are discussed.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hal E. Beck, Hal E. Beck, Daniel Bergondy, Daniel Bergondy, Joe R. Brown, Joe R. Brown, Hamed Sari-Sarraf, Hamed Sari-Sarraf, } "Multiresolution segmentation of forward-looking IR and SAR imagery using neural networks", Proc. SPIE 1381, Intelligent Robots and Computer Vision IX: Algorithms and Techniques, (1 February 1991); doi: 10.1117/12.25191; https://doi.org/10.1117/12.25191
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Geometry Guided Segmentation
Proceedings of SPIE (March 26 1989)
Integration of segmentation and stereo matching
Proceedings of SPIE (October 21 1993)
Segmentation using models of expected structure
Proceedings of SPIE (January 31 1991)
Range image segmentation using regularization
Proceedings of SPIE (January 31 1992)

Back to Top